whatmodel.sh / GPT-4 Turbo Preview (0125)

GPT-4 Turbo Preview (0125)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

GPT-4 Turbo Preview (0125) is a closed-weights language model from OpenAI, released January 2024. Licence: proprietary.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2024-01-25). Dated API snapshot gpt-4-0125-preview. OpenAI deprecations page: shut down 2026-03-26. Epoch model_metadata groups it under 'GPT-4 Turbo (Nov 2023)'; kept distinct from gpt-4-1106-preview because the snapshot differs.

53.6±0.7comparison only: no current run option verifiedfrom 16 benchmark results across 9 sources

$ how it compares

The LLMs ranked either side of GPT-4 Turbo Preview (0125), out of 828 with a score, then more from OpenAI.

#modelscorewhereRAMreleased
342Mistral Small 3.1 24B (2503) Mistral54±1local~17GB2025-03
343GPT-4 Turbo Preview (1106) OpenAI54±1comparison only2023-11
344GPT-4 Turbo Preview (0125) OpenAI54±1comparison only2024-01
345Claude 3.5 Haiku Anthropic54±1comparison only2024-10
346Llama 3.1 Tulu 3 70B Ai254±1local~43GB2024-11
more from OpenAI
1GPT-6 Astra OpenAI87±1api $20.00/M2026-09
3GPT-6.1 Sol OpenAI85±1api $4.00/M2026-09
7GPT-6 Sol OpenAI83±1api $4.00/M2026-09

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▅▇█▇▅▄▃▁ #258 of 524 · 19% of its score · 3 tests

Beats Qwen3.5 4B, Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B) here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 3B Reasoning 2512, DeepSeek-Coder-V2 Instruct (0724) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval83.5% ✎▁█▄▅▇█·▄▇▅▄▄ beats 42/42easy · avg 78%▇▇▇▇ 11%sharp
Aider code editing (133 Exercism Python exercises, two attempts)66.2% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 41/62medium · avg 54%▇▇▇ 7.0%at its level
HumanEval (simple-evals) lab86.6% ✎▆█▆▆▂··▂···▂ beats 1/15easy · avg 84%▇ 1.4%typical
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #237 of 463 · 18% of its score · 3 tests

Beats Granite 4.2 8B, Qwen3-VL 30B-A3B Thinking, Mistral Small 4 (119B-A6.5B) here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Gemma 3n E4B, LFM2.5 1.2B Thinking here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena-Hard (v0.1, GPT-4-1106 judge)78.0% ✎▂▁▁▅█▅▄▃▃▅▃▁ beats 51/60medium · avg 52%▇▇▇▇ 10%sharp · at its level
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1255.0 ✎▂▁▂▁▃▇█▆▇▄▃▂ beats 90/95avg 1201▇▇ 3.9%blunt
LMArena (text)1313.2 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 142/379avg 1268▇▇ 3.9%blunt
math▁▂▃▅▇▅▅█▄▁▁▁ #324 of 462 · 13% of its score · 3 tests

Beats Molmo 2 8B here, though they rank higher overall. Trails DeepSeek R1 Distill Qwen 1.5B, Granite 8B Code Base (4K), Mixtral 8x7B v0.1 (base) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MATH level 535.4% ✎▂▂▅▆▄█▆▃▅▂▃▄ beats 27/92hard · avg 32%▇▇▇▇ 10%sharp · at its level
MATH (simple-evals, original test set, pre-o1 rows) lab64.5% ✎█····▄··▄··█ beats 1/5medium · avg 63%▇ 1.9%at its level
MGSM (simple-evals) lab85.1% ✎▁····▃▅▁█▁▃▁ beats 1/16easy · avg 82%▇ 1.5%blunt
other tests7 not in a task · 50% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-2648.9% ✎▁▁▁▂▂▃▂█▆▃▅▃ beats 52/61medium · avg 41%▇▇▇▇▇▇▇ 17%at its level
EvoEval (overall)65.1% ✎▂▂▃▄▄█▁▄▅▃▁▃ beats 41/42medium · avg 55%▇▇▇▇▇ 12%at its level
GPQA Diamond (simple-evals) lab41.4% ✎█▃▃█·▃▃▅▃▃▃▅ beats 1/16hard · avg 40%▇▇▇ 7.4%sharp · at its level
GPQA Diamond42.3% ✎▁▁▁▁▂▄▆▄▅▇█▅ beats 45/208hard · avg 40%▇▇ 5.9%sharp · at its level
WildBench v2 WB-Score (task macro)52.2775 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 42/52avg 45.199 WB-Score▇▇ 4.4%sharp
MMLU (simple-evals, zero-shot CoT) lab85.4% ✎▂▂·█▄▄▂·█▂·▂ beats 4/16easy · avg 80%▇ 3.0%typical
DROP F1, 3-shot (simple-evals) lab81.5% ✎▂▂▄▆▆█·▂···▄ beats 7/16easy · avg 78%▇ 0.4%blunt

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · Top Leaderboard Ranking = Top… 22%, LiveBench model judgments (HF… 17%, Epoch AI — internal evaluatio… 16% and 6 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2▇▇▇▇▇▇▇ 22%CC BY 4.0
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇▇▇▇▇ 17%Apache-2.0 (stated in the LiveBench datasheet)
Epoch AI — internal evaluations2▇▇▇▇▇ 16%CC BY 4.0
OpenAI simple-evals README benchmark results (OpenAI's own models) · lab-reported6▇▇▇▇▇ 16%MIT
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)1▇▇▇ 10%Apache-2.0
Aider code editing benchmark runs (old edit leaderboard)1▇▇ 7%Apache-2.0
WildBench v2 leaderboard data (Ai2)1▇ 4%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇ 4%CC-BY-4.0
LMArena leaderboard dataset1▇ 4%CC BY 4.0
prior · pull toward the middle▇ 0%
weighted average= 53.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json